© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10437
    Prev
    Next
    INDEX
    Explanations

    references to championship titles

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    IUrlHelper
    -0.75
     Championship
    -0.71
    Personendaten
    -0.59
     heroes
    -0.57
    NavController
    -0.57
     hero
    -0.56
    reportWebVitals
    -0.56
    findpost
    -0.54
     Hero
    -0.54
    évaluateur
    -0.54
    POSITIVE LOGITS
     champion
    2.66
    champion
    2.17
     Champion
    1.86
     champions
    1.83
    Champion
    1.77
     campeones
    1.41
     champ
    1.23
     campeão
    1.23
     campeón
    1.19
     campione
    1.05
    Activations Density 0.005%

    No Known Activations